Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data. To address these issues, we propose UDPReg, an unsupervised deep probabilistic registration framework for point clouds with partial overlaps. Specifically, we first adopt a network to learn posterior probability distributions of Gaussian mixture models (GMMs) from point clouds. To handle partial point cloud registration, we apply the Sinkhorn algorithm to predict the distribution-level correspondences under the constraint of the mixing weights of GMMs. To enable unsupervised learning, we design three distribution consistency-based losses: self-consistency, cross-consistency, and local contrastive. The self-consistency loss is formulated by encouraging GMMs in Euclidean and feature spaces to share identical posterior distributions. The cross-consistency loss derives from the fact that the points of two partially overlapping point clouds belonging to the same clusters share the cluster centroids. The cross-consistency loss allows the network to flexibly learn a transformation-invariant posterior distribution of two aligned point clouds. The local contrastive loss facilitates the network to extract discriminative local features. Our UDPReg achieves competitive performance on the 3DMatch/3DLoMatch and ModelNet/ModelLoNet benchmarks.

翻译：深度点云配准方法在处理部分重叠时面临挑战，且依赖标注数据。为解决这些问题，我们提出UDPReg——一种用于部分重叠点云的无监督深度概率配准框架。具体而言，我们首先采用网络从点云中学习高斯混合模型（GMM）的后验概率分布。为处理部分点云配准，我们应用Sinkhorn算法在GMM混合权重约束下预测分布级对应关系。为实现无监督学习，我们设计了三种基于分布一致性的损失函数：自一致性损失、交叉一致性损失和局部对比损失。自一致性损失通过促使欧氏空间与特征空间中的GMM共享相同后验分布来构建。交叉一致性损失源于以下事实：属于同一簇的两个部分重叠点云中的点共享簇质心。该损失使网络能够灵活学习配准后两个点云的变换不变后验分布。局部对比损失促进网络提取具有判别性的局部特征。我们的UDPReg在3DMatch/3DLoMatch和ModelNet/ModelLoNet基准上取得了具有竞争力的性能。